Explainability of Text Processing and Retrieval Methods: A Survey
ACM Computing Surveys · 30.08.2026 · 58 (11) · 1-48
DOI: 10.1145/3801957 ↗Kurz gefasst
Fachartikel in der Zeitschrift ACM Computing Surveys, online erschienen am 01.05.2026. Verfasst von Sourav Saha und 2 weiteren Autor:innen. Die Arbeit nennt 220 Literaturangaben. Gefördert von: TCS Research Scholar program.
Abstract (Originalsprache)
Deep Learning and Machine Learning based models have become extremely popular in text processing and information retrieval, owing to their remarkable effectiveness. However, the complex non-linear structures underlying these models make them largely inscrutable. A significant body of research has focused on increasing the transparency of these models. This article provides a broad overview of research on the explainability and interpretability of information retrieval methods, focusing primarily on both neural models for document ranking, and retrieval-augmented generation systems. A significant part of this research is inspired by, and strongly related to, similar work done in the area of natural language processing (NLP). For completeness, therefore, we also briefly review (in the Appendices) some recent studies from the NLP community on explaining word embeddings, sequence modeling, attention modules, transformers, and BERT. The concluding section suggests some possible directions for future research on this topic.
Förderung
- TCS Research Scholar program
Zitieren
APA
Saha, S., Majumdar, D., & Mitra, M. (2026). Explainability of Text Processing and Retrieval Methods: A Survey. ACM Computing Surveys, 58(11), 1-48. https://doi.org/10.1145/3801957
Vancouver
Saha S, Majumdar D, Mitra M. Explainability of Text Processing and Retrieval Methods: A Survey. ACM Computing Surveys. 2026;58(11):1-48. doi:10.1145/3801957
BibTeX
@article{Saha2026,
author = {Saha, Sourav and Majumdar, Debapriyo and Mitra, Mandar},
title = {Explainability of Text Processing and Retrieval Methods: A Survey},
journal = {ACM Computing Surveys},
year = {2026},
volume = {58},
number = {11},
pages = {1--48},
doi = {10.1145/3801957}
}
EUVIMED